Zero-Shot Font Style Transfer with a Differentiable Renderer
Zero-Shot Font Style Transfer with a Differentiable Renderer
复制标题
DOI：
10.1145/3551626.3564961
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Kota Izumi;Keiji Yanai
中科院分区：
文献类型：
--
作者：
Kota Izumi;Keiji Yanai
近年来，一种大规模的语言-图像多模态模型CLIP被用于实现基于语言的图像翻译，无需训练。在本研究中，我们尝试使用CLIP为字体图像生成基于语言的装饰字体。在现有的使用CLIP的图像样式转移方法中，风格化的字体图像通常只是被装饰包围，字符本身并没有明显的变化。另一方面，在本研究中，我们使用CLIP和矢量图形图像表示，使用可微分渲染器来实现与输入文本匹配的文本图像的样式转移。实验结果表明，该方法可以将字体图像的样式转移到与给定文本相匹配的位置。除了文本图像，我们证实了所提出的方法也能够根据给定的文本转换简单的标志图案的风格。
Recently, a large-scale language-image multi-modal model, CLIP, has been used to realize language-based image translation in a zero-shot manner without training. In this study, we attempted to generate language-based decorative fonts for font images using CLIP. By the existing image style transfer methods using CLIP, stylized font images are usually only surrounded by decorations, and the characters themselves do not change significantly. On the other hand, in this study, we use CLIP and vector graphics image representation using a differentiable renderer to achieve a style transfer of text images that matches the input text. The experimental results show that the proposed method transfers the style of font images to match the given texts. In addition to text images, we confirmed that the proposed method was also able to transform the style of simple logo patterns based on the given texts.